pulsemcp Safe content atomic mcp-remote

Python Code Execution

MCP server implementation by Pydantic that provides secure Python code execution in a sandboxed environment using Pyodide running in Deno. The server offers a single `run_python_code` tool that executes Python code with dependency installation support, capturing stdout/stderr and return values while maintaining isolation from the host system. Built with TypeScript for the Deno runtime and Python for the client interface, it supports both stdio and HTTP transports, automatic dependency management through micropip, and includes comprehensive error handling for installation and runtime failures. Designed for AI assistants that need to perform data analysis, mathematical computations, or general Python scripting tasks without security risks to the underlying system.

Cognium trust score

50%

Tier

Unverified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: security
Source: PulseMCP
Repository: github.com/pydantic/mcp-run-python
Author type: human
Updated: 2026-04-29

View source Find related skills

MCP

Resolve Python Code Execution from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"